Cited by 122Artificial Intelligence in EducationIntelligent Tutoring Systems and Adaptive LearningArtificial Intelligence in Healthcare and Education

ChatGPT has Aced the Test of Understanding in College Economics: Now What?

Open access
Geerling, Wayne, Mateer, G. Dirk, Wooten, Jadrian, Damodaran, Nikhil·2023·The American Economist

Abstract

The Test of Understanding in College Economics (TUCE) is a standardized test of economics knowledge performed in the United States which primarily targets principles-level understanding. We asked ChatGPT to complete the TUCE. ChatGPT ranked in the 91st percentile for Microeconomics and the 99th percentile for Macroeconomics when compared to students who take the TUCE exam at the end of their principles course. The results show that ChatGPT is capable of providing answers that exceed the mean responses of students across all institutions. The emergence of artificial intelligence presents a significant challenge to traditional assessment methods in higher education. An important implication of this finding is that educators will likely need to redesign their curriculum in at least one of the following three ways: reintroduce proctored, in-person assessments; augment learning with chatbots; and/or increase the prevalence of experiential learning projects that artificial intelligence struggles to replicate well.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1177/05694345231169654

Cites

34 of 35 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Generative AI has demonstrated human-level performance on a broad range of tasks.

    “Generative AI, such as OpenAI’s ChatGPT, has rapidly emerged as a disruptive technology capable of achieving human-level performance on a broad range of tasks (1–5).”

    From Generative AI without guardrails can harm learning: Evidence from high school mathematics (2025) · cites this paper as [4]

    The Introduction (pp. 1–2) describes ChatGPT responses as often indistinguishable from human writing and reports above-average test performance across several academic fields. The Conclusion (p. 9) reports its high scores on college economics tests. These passages support human-level performance on academic assessments, but not the broader claim across a wide range of task types or generative AI systems generally. (LLM, conf=0.83)

    Experimental — accuracy not yet measured
  • ChatGPT scores in the 90th percentile on standardized exams.

    “In economics education, Geerling et al. (2023) demonstrate that ChatGPT scores in the 90th percentile on standardized exams, showing how easily it can produce high-quality academic work without genuine student engagement.”

    From Generative AI-Enhanced Oral Exams in Economics Education (2026) · cites this paper as Geerling et al. (2023)

    The Conclusion (p. 9) reports that ChatGPT ranked at the 91st percentile in microeconomics and the 99th percentile in macroeconomics on the standardized TUCE exams. This supports the claim of high exam performance, but “the 90th percentile” obscures the distinct results, and the study does not establish performance on standardized exams generally. (LLM, conf=0.85)

    Experimental — accuracy not yet measured
  • Building supportive and engaging learning environments that complement traditional pedagogical methods can provide a dynamic and interactive platform to foster knowledge acquisition and acknowledge existing concerns on plagiarism and academic integrity.

    “An alternative to using GenAI in education, beyond exams and assignment writing, is building supportive and engaging learning environments that complement traditional pedagogical methods. This proposition can provide a dynamic and interactive platform to foster knowledge acquisition and acknowledge the existing concerns on plagiarism and academic integrity [8,16].”
  • ChatGPT can provide answers in exams that exceed the mean responses of students, which poses a significant challenge to traditional assessment methods in higher education.

    “Some recent research results show that ChatGPT can provide answers in exams that exceed the mean responses of students, which poses a significant challenge to traditional assessment methods in HE [8].”
  • ChatGPT performs well in exams in disciplines such as engineering, economics, medicine, and geography.

    “Related research shows that ChatGPT performs well in exams in disciplines such as engineering (Uhlig et al., 2023), economics (Geerling et al., 2023), medicine (Currie et al., 2023), and geography (Stutz et al., 2023), indicating that the issue of academic integrity in higher education is facing unprecedented challenges.”

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 3

  1. Al-Bahrani, A., Holder, K., Patel, D., & Wooten, J. (2016). Art of econ: Incorporating the arts through active learning assignments in principles courses. Journal of Economics and Finance Education , 15 (2), 1 -16.
  2. Batane, T. (2010). Turning to Turnitin to fight plagiarism among university students. Journal of Educational Technology and Society , 13 (2), 1 -12.
  3. Goel, A. K., & Polepeddi, L. (2018). Jill Watson: A virtual teaching assistant for online education. In Learning engineering for online education (pp. 120 -143). Routledge.

Cited by

Sorted by citations

Authors
Geerling, W., Mateer, G. D., Wooten, J., & Damodaran, N.
Affiliations
  • The University of Texas at Austin (US)
  • Virginia Tech (US)
  • O. P. Jindal Global University (IN)
Corresponding author
Geerling, Wayne
Venue
The American Economist
Published
2023-04-08
Volume
68
Issue
2
Pages
233-245
ISSN
  • 0569-4345 (ISSN-L)
  • 2328-1235
OpenAlex
W4362723020
Cited by
119
References
34
Citations by year
2026: 15 · 2025: 38 · 2024: 38 · 2023: 28
FWCI
27.93
Type
journal article
Language
en
Open access
Locations
  • The American Economist (publishedVersion, cc-by)
  • VTechWorks (Virginia Tech) (submittedVersion, cc-by)
  • RePEc: Research Papers in Economics (submittedVersion)
Topics
  • Physical Sciences › Computer Science › Information Systems › Artificial Intelligence in Education
  • Physical Sciences › Computer Science › Artificial Intelligence › Intelligent Tutoring Systems and Adaptive Learning
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
Keywords
ChatGPT, economics education, artificial intelligence in education, automated assessment, microeconomics, macroeconomics, economic principles, chatbots, experiential learning, curriculum redesign

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review